How to Find Contours in OpenCV for Computer Vision

To find contours in OpenCV, use the cv2.findContours() function on a binary image. This function returns contours and their hierarchy, which you can use to analyze shapes or objects in the image.

Syntax

The basic syntax of cv2.findContours() is:

• image: A binary image (usually after thresholding or edge detection).
• mode: Contour retrieval mode (e.g., cv2.RETR_EXTERNAL to get only outer contours).
• method: Contour approximation method (e.g., cv2.CHAIN_APPROX_SIMPLE to compress horizontal, vertical, and diagonal segments).

The function returns contours and hierarchy information.

python

contours, hierarchy = cv2.findContours(image, mode, method)

Example

This example shows how to load an image, convert it to grayscale, apply thresholding to get a binary image, find contours, and draw them on the original image.

python

import cv2

# Load image
img = cv2.imread('shapes.png')

# Convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# Apply binary threshold
_, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)

# Find contours
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

# Draw contours on the original image
cv2.drawContours(img, contours, -1, (0, 255, 0), 3)

# Save the result image
cv2.imwrite('contours_output.png', img)

# Print number of contours found
print(f'Number of contours found: {len(contours)}')

Output

Number of contours found: 3

Common Pitfalls

• Passing a non-binary image to cv2.findContours() will not work correctly; always threshold or edge-detect first.
• OpenCV versions before 4.0 return three values from findContours(), but newer versions return two; use unpacking accordingly.
• Using the wrong contour retrieval mode can miss inner contours or hierarchy details.

python

import cv2

# Wrong: Using a color image directly
img = cv2.imread('shapes.png')
contours, hierarchy = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)  # This will fail or give wrong results

# Right: Convert to grayscale and threshold first
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

Quick Reference

Parameter	Description	Common Values
image	Binary image to find contours on	Thresholded or edge-detected image
mode	Contour retrieval mode	cv2.RETR_EXTERNAL, cv2.RETR_LIST, cv2.RETR_TREE
method	Contour approximation method	cv2.CHAIN_APPROX_NONE, cv2.CHAIN_APPROX_SIMPLE
returns	Contours and hierarchy	List of contours, hierarchy array

Key Takeaways

Always use a binary image (thresholded or edge-detected) as input to cv2.findContours().

Use cv2.RETR_EXTERNAL to get only outer contours or cv2.RETR_TREE for full hierarchy.

cv2.CHAIN_APPROX_SIMPLE reduces contour points to save memory without losing shape.

Check OpenCV version for correct unpacking of findContours() return values.

Draw contours with cv2.drawContours() to visualize detected shapes.